def quant_from_peak_df(peak_df, gff3, fa_dict, organism=None):
count1 = 0
count2 = 0
pssm = SP.generate_consensus_matrix(gff3, fa_dict, PSSM=True)
ss_dict, flag = SP.list_splice_sites(gff3, organism=organism)
ss_dict = SP.collapse_ss_dict(ss_dict)
quant_df = peak_df[(peak_df['type'] != '3prime') & (peak_df['looks like'] != 'AG')]
quant_df['genome coord'] = quant_df['chromosome'].str.cat(quant_df['position'].values.astype(str), sep=':')
quant_df.index = quant_df['genome coord']
quant_df = quant_df.drop('index', axis=1)
column_dict = {'intron size':[], 'alt splicing':[], '5p score':[], '3p score':[], 'seq5':[], 'seq3':[]}
new_index = []
seq5 = []
seq3 = []
for coord in quant_df.index:
coord_df = quant_df[quant_df.index == coord]
three_site = None
alt3 = False
if len(coord_df) > 0:
coord_df = coord_df.sort_values('height', ascending=False).ix[0]
introns = ss_dict[coord_df['transcript']]
if 'prime' in coord_df['type']:
peak_range = range(coord_df['position']-5,coord_df['position']+5)
for intron in introns:
if intron[0] in peak_range:
five_site = intron[0]
three_site = intron[1]
break
if len(quant_df[(quant_df['transcript'] == coord_df['transcript']) & (quant_df['type'] == 'AG')]) > 0:
alt3=True
else:
if 'AG' in quant_df[quant_df['transcript'] == coord_df['transcript']]['type']:
five_site = coord_df['position']
three_df = quant_df[(quant_df['transcript'] == coord_df['transcript']) & (quant_df['type'] == 'AG')]
three_df = three_df.sort_values('height', ascending=False)
three_site = three_df.ix[0]['position']
if three_site is not None:
new_index.append(coord)
size = abs(three_site-five_site)/1000.
column_dict['intron size'].append(size)
column_dict['alt splicing'].append(alt3)
if coord_df['strand'] == '+':
s5 = fa_dict[coord_df['chromosome']][five_site-2:five_site+6]
s3 = fa_dict[coord_df['chromosome']][three_site-6:three_site+2]
elif coord_df['strand'] == '-':
s5 = fa_dict[coord_df['chromosome']][five_site-6:five_site+2]
s5 = SP.reverse_complement(s5)
s3 = fa_dict[coord_df['chromosome']][three_site-2:three_site+6]
s3 = SP.reverse_complement(s3)
column_dict['seq5'].append(s5)
column_dict['seq3'].append(s3)
scores = SP.simple_score_junction(s5, s3, pssm)
column_dict['3p score'].append(scores[1])
column_dict['5p score'].append(scores[0])
new_quant_df = quant_df[quant_df.index.isin(new_index)][['genome coord','chromosome',
'strand','transcript','position','type']]
for column, data in column_dict.iteritems():
new_quant_df[column] = data
new_quant_df = new_quant_df.drop_duplicates(subset='genome coord', keep='first').set_index('genome coord')
new_quant_df = SP.backfill_splice_sites(new_quant_df, gff3, fa_dict, pssm, organism=organism)
#for n in range(len(new_quant_df['seq5'].iloc[0])):
# new_quant_df['Base 5-'+str(n)] = [x[n] for x in new_quant_df['seq5']]
#for n in range(len(new_quant_df['seq3'].iloc[0])):
# new_quant_df['Base 3-'+str(n)] = [x[n] for x in new_quant_df['seq3']]
#new_quant_df = new_quant_df.drop(['seq5','seq3'], axis=1)
new_quant_df = SP.find_score_branches_ppy(new_quant_df, '/home/jordan/GENOMES/S288C/S288C_branches2.txt', fa_dict)
return new_quant_df
def make_quant_df(junc_df, branch_df, gff3, fa_dict, organism=None):
pssm = SP.generate_consensus_matrix(gff3, fa_dict, PSSM=True)
quant_df = junc_df[(junc_df['type'] != '3prime') & (junc_df['looks like'] != 'AG')]
new_intron_size = []
alt_splice = []
score_3 = []
score_5 = []
seq5 = []
seq3 = []
new_quant_df = pd.DataFrame(index=set(quant_df.index), columns=['intron size','alt splicing'])
for coord in new_quant_df.index:
coord_df = quant_df[quant_df.index == coord]
#Determine if multiple junctions come from this peak
if len(coord_df) > 1: alt_splice.append(True)
else: alt_splice.append(False)
if max(coord_df['annotated intron size']) > 0:
coord_df = coord_df.sort_values('annotated intron size', ascending=False)
new_intron_size.append(coord_df.ix[0]['annotated intron size']/1000.)
seq5.append(coord_df.ix[0]['junction sequence1'])
seq3.append(coord_df.ix[0]['junction sequence2'])
score_3.append(coord_df.ix[0]['annotated 3p score'])
score_5.append(coord_df.ix[0]['annotated 5p score'])
else:
coord_df = coord_df.sort_values('junction size', ascending=False)
new_intron_size.append(coord_df.ix[0]['junction size']/1000.)
seq5.append(coord_df.ix[0]['junction sequence1'])
seq3.append(coord_df.ix[0]['junction sequence2'])
scores = SP.simple_score_junction(coord_df.ix[0]['junction sequence1'], coord_df.ix[0]['junction sequence2'], pssm)
score_3.append(scores[1])
score_5.append(scores[0])
new_quant_df['intron size'] = new_intron_size
new_quant_df['alt splicing'] = alt_splice
new_quant_df['5p score'] = score_5
new_quant_df['3p score'] = score_3
new_quant_df['seq5'] = seq5
new_quant_df['seq3'] = seq3
quant_df = quant_df.sort_values('annotated intron size')
quant_df = quant_df.reset_index(drop=True).drop_duplicates(subset='genome coord', keep='first').set_index('genome coord')
new_quant_df = new_quant_df.merge(quant_df[['transcript','chromosome','position','strand','type']], right_index=True, left_index=True)
for coord in set(branch_df['genome coord']):
if coord not in new_quant_df.index:
coord_df = branch_df[branch_df['genome coord'] == coord]
coord_df = coord_df.sort_values('depth')
best = coord_df.iloc[0]
coord_dict = {'transcript':best['transcript'][:-2],
'chromosome':best['chromosome'],
'position':best['5p splice site'],
'strand':best['strand'],
'type':best['type'],
'intron size':best['intron size'],
'alt splicing':np.where(len(coord_df)> 1, True, False),
'5p score':np.NaN,
'3p score':np.NaN,
'seq5':'','seq3':''}
if len(best['5p seq']) > 0:
coord_dict['seq5'] = best['5p seq']
else:
if best['strand'] == '+':
coord_dict['seq5'] = fa_dict[best['chromosome']][(int(best['5p splice site'])-1):(int(best['5p splice site'])+7)]
elif best['strand'] == '-':
coord_dict['seq5'] = fa_dict[best['chromosome']][(int(best['5p splice site'])-6):(int(best['5p splice site'])+2)]
coord_dict['seq5'] = SP.reverse_complement(coord_dict['seq5'])
if str(best['3p splice site']) != 'nan':
three_site = best['3p splice site']
else:
if best['strand'] == '+':
after_branch = fa_dict[best['chromosome']][best['branch site']:best['branch site']+100]
elif best['strand'] == '-':
after_branch = fa_dict[best['chromosome']][best['branch site']-100:best['branch site']]
after_branch = SP.reverse_complement(after_branch)
for subs in ['TAG','CAG','GAG','AAG']:
if subs in after_branch:
ix = after_branch.find(subs)+3
break
three_site = best['branch site']+ix
if best['strand'] == '-':
three_site = best['branch site']-ix
coord_dict['intron size'] = abs(coord_dict['position']-three_site)
if best['strand'] == '+':
coord_dict['seq3'] = fa_dict[best['chromosome']][int(three_site-5):int(three_site)+3]
elif best['strand'] == '-':
coord_dict['seq3'] = fa_dict[best['chromosome']][int(three_site)-2:int(three_site)+6]
coord_dict['seq3'] = SP.reverse_complement(coord_dict['seq3'])
coord_dict['5p score'], coord_dict['3p score'] = SP.simple_score_junction(coord_dict['seq5'], coord_dict['seq3'], pssm)
coord_s = pd.Series(coord_dict, name=coord)
new_quant_df = new_quant_df.append(coord_s)
new_quant_df = backfill_splice_sites(new_quant_df, gff3, fa_dict, pssm, organism=organism)
for n in range(len(new_quant_df['seq5'].iloc[0])):
new_quant_df['Base 5-'+str(n)] = [x[n] for x in new_quant_df['seq5']]
for n in range(len(new_quant_df['seq3'].iloc[0])):
new_quant_df['Base 3-'+str(n)] = [x[n] for x in new_quant_df['seq3']]
new_quant_df = new_quant_df.drop(['seq5','seq3'], axis=1)
lariat_df = junc_df[(junc_df['type'] == '3prime') | (junc_df['looks like'] == 'AG')]
lariat_df = lariat_df.sort_values(['genome coord','annotated intron size'], ascending=False)
lariat_df = lariat_df.reset_index(drop=True).drop_duplicates(subset='genome coord', keep='first').set_index('genome coord')
lariat_df = lariat_df[['transcript','chromosome','position','strand','type']]
return new_quant_df, lariat_df
def make_quant_df(junc_df, branch_df, gff3, fa_dict, organism=None):
pssm = SP.generate_consensus_matrix(gff3, fa_dict, PSSM=True)
quant_df = junc_df[(junc_df['type'] != '3prime')
& (junc_df['looks like'] != 'AG')]
new_intron_size = []
alt_splice = []
score_3 = []
score_5 = []
seq5 = []
seq3 = []
new_quant_df = pd.DataFrame(index=set(quant_df.index),
columns=['intron size', 'alt splicing'])
for coord in new_quant_df.index:
coord_df = quant_df[quant_df.index == coord]
#Determine if multiple junctions come from this peak
if len(coord_df) > 1: alt_splice.append(True)
else: alt_splice.append(False)
if max(coord_df['annotated intron size']) > 0:
coord_df = coord_df.sort_values('annotated intron size',
ascending=False)
new_intron_size.append(coord_df.ix[0]['annotated intron size'] /
1000.)
seq5.append(coord_df.ix[0]['junction sequence1'])
seq3.append(coord_df.ix[0]['junction sequence2'])
score_3.append(coord_df.ix[0]['annotated 3p score'])
score_5.append(coord_df.ix[0]['annotated 5p score'])
else:
coord_df = coord_df.sort_values('junction size', ascending=False)
new_intron_size.append(coord_df.ix[0]['junction size'] / 1000.)
seq5.append(coord_df.ix[0]['junction sequence1'])
seq3.append(coord_df.ix[0]['junction sequence2'])
scores = SP.simple_score_junction(
coord_df.ix[0]['junction sequence1'],
coord_df.ix[0]['junction sequence2'], pssm)
score_3.append(scores[1])
score_5.append(scores[0])
new_quant_df['intron size'] = new_intron_size
new_quant_df['alt splicing'] = alt_splice
new_quant_df['5p score'] = score_5
new_quant_df['3p score'] = score_3
new_quant_df['seq5'] = seq5
new_quant_df['seq3'] = seq3
quant_df = quant_df.sort_values('annotated intron size')
quant_df = quant_df.reset_index(drop=True).drop_duplicates(
subset='genome coord', keep='first').set_index('genome coord')
new_quant_df = new_quant_df.merge(
quant_df[['transcript', 'chromosome', 'position', 'strand', 'type']],
right_index=True,
left_index=True)
for coord in set(branch_df['genome coord']):
if coord not in new_quant_df.index:
coord_df = branch_df[branch_df['genome coord'] == coord]
coord_df = coord_df.sort_values('depth')
best = coord_df.iloc[0]
coord_dict = {
'transcript': best['transcript'][:-2],
'chromosome': best['chromosome'],
'position': best['5p splice site'],
'strand': best['strand'],
'type': best['type'],
'intron size': best['intron size'],
'alt splicing': np.where(len(coord_df) > 1, True, False),
'5p score': np.NaN,
'3p score': np.NaN,
'seq5': '',
'seq3': ''
}
if len(best['5p seq']) > 0:
coord_dict['seq5'] = best['5p seq']
else:
if best['strand'] == '+':
coord_dict['seq5'] = fa_dict[best['chromosome']][(
int(best['5p splice site']) -
1):(int(best['5p splice site']) + 7)]
elif best['strand'] == '-':
coord_dict['seq5'] = fa_dict[best['chromosome']][(
int(best['5p splice site']) -
6):(int(best['5p splice site']) + 2)]
coord_dict['seq5'] = SP.reverse_complement(
coord_dict['seq5'])
if str(best['3p splice site']) != 'nan':
three_site = best['3p splice site']
else:
if best['strand'] == '+':
after_branch = fa_dict[best['chromosome']][
best['branch site']:best['branch site'] + 100]
elif best['strand'] == '-':
after_branch = fa_dict[
best['chromosome']][best['branch site'] -
100:best['branch site']]
after_branch = SP.reverse_complement(after_branch)
for subs in ['TAG', 'CAG', 'GAG', 'AAG']:
if subs in after_branch:
ix = after_branch.find(subs) + 3
break
three_site = best['branch site'] + ix
if best['strand'] == '-':
three_site = best['branch site'] - ix
coord_dict['intron size'] = abs(coord_dict['position'] -
three_site)
if best['strand'] == '+':
coord_dict['seq3'] = fa_dict[
best['chromosome']][int(three_site - 5):int(three_site) +
3]
elif best['strand'] == '-':
coord_dict['seq3'] = fa_dict[
best['chromosome']][int(three_site) - 2:int(three_site) +
6]
coord_dict['seq3'] = SP.reverse_complement(coord_dict['seq3'])
coord_dict['5p score'], coord_dict[
'3p score'] = SP.simple_score_junction(coord_dict['seq5'],
coord_dict['seq3'],
pssm)
coord_s = pd.Series(coord_dict, name=coord)
new_quant_df = new_quant_df.append(coord_s)
new_quant_df = backfill_splice_sites(new_quant_df,
gff3,
fa_dict,
pssm,
organism=organism)
for n in range(len(new_quant_df['seq5'].iloc[0])):
new_quant_df['Base 5-' + str(n)] = [x[n] for x in new_quant_df['seq5']]
for n in range(len(new_quant_df['seq3'].iloc[0])):
new_quant_df['Base 3-' + str(n)] = [x[n] for x in new_quant_df['seq3']]
new_quant_df = new_quant_df.drop(['seq5', 'seq3'], axis=1)
lariat_df = junc_df[(junc_df['type'] == '3prime') |
(junc_df['looks like'] == 'AG')]
lariat_df = lariat_df.sort_values(
['genome coord', 'annotated intron size'], ascending=False)
lariat_df = lariat_df.reset_index(drop=True).drop_duplicates(
subset='genome coord', keep='first').set_index('genome coord')
lariat_df = lariat_df[[
'transcript', 'chromosome', 'position', 'strand', 'type'
]]
return new_quant_df, lariat_df
def quant_from_peak_df(peak_df, gff3, fa_dict, organism=None):
count1 = 0
count2 = 0
pssm = SP.generate_consensus_matrix(gff3, fa_dict, PSSM=True)
ss_dict, flag = SP.list_splice_sites(gff3, organism=organism)
ss_dict = SP.collapse_ss_dict(ss_dict)
quant_df = peak_df[(peak_df['type'] != '3prime')
& (peak_df['looks like'] != 'AG')]
quant_df['genome coord'] = quant_df['chromosome'].str.cat(
quant_df['position'].values.astype(str), sep=':')
quant_df.index = quant_df['genome coord']
quant_df = quant_df.drop('index', axis=1)
column_dict = {
'intron size': [],
'alt splicing': [],
'5p score': [],
'3p score': [],
'seq5': [],
'seq3': []
}
new_index = []
seq5 = []
seq3 = []
for coord in quant_df.index:
coord_df = quant_df[quant_df.index == coord]
three_site = None
alt3 = False
if len(coord_df) > 0:
coord_df = coord_df.sort_values('height', ascending=False).ix[0]
introns = ss_dict[coord_df['transcript']]
if 'prime' in coord_df['type']:
peak_range = range(coord_df['position'] - 5,
coord_df['position'] + 5)
for intron in introns:
if intron[0] in peak_range:
five_site = intron[0]
three_site = intron[1]
break
if len(quant_df[(quant_df['transcript'] == coord_df['transcript'])
& (quant_df['type'] == 'AG')]) > 0:
alt3 = True
else:
if 'AG' in quant_df[quant_df['transcript'] ==
coord_df['transcript']]['type']:
five_site = coord_df['position']
three_df = quant_df[
(quant_df['transcript'] == coord_df['transcript'])
& (quant_df['type'] == 'AG')]
three_df = three_df.sort_values('height', ascending=False)
three_site = three_df.ix[0]['position']
if three_site is not None:
new_index.append(coord)
size = abs(three_site - five_site) / 1000.
column_dict['intron size'].append(size)
column_dict['alt splicing'].append(alt3)
if coord_df['strand'] == '+':
s5 = fa_dict[coord_df['chromosome']][five_site - 2:five_site +
6]
s3 = fa_dict[coord_df['chromosome']][three_site -
6:three_site + 2]
elif coord_df['strand'] == '-':
s5 = fa_dict[coord_df['chromosome']][five_site - 6:five_site +
2]
s5 = SP.reverse_complement(s5)
s3 = fa_dict[coord_df['chromosome']][three_site -
2:three_site + 6]
s3 = SP.reverse_complement(s3)
column_dict['seq5'].append(s5)
column_dict['seq3'].append(s3)
scores = SP.simple_score_junction(s5, s3, pssm)
column_dict['3p score'].append(scores[1])
column_dict['5p score'].append(scores[0])
new_quant_df = quant_df[quant_df.index.isin(new_index)][[
'genome coord', 'chromosome', 'strand', 'transcript', 'position',
'type'
]]
for column, data in column_dict.iteritems():
new_quant_df[column] = data
new_quant_df = new_quant_df.drop_duplicates(
subset='genome coord', keep='first').set_index('genome coord')
new_quant_df = SP.backfill_splice_sites(new_quant_df,
gff3,
fa_dict,
pssm,
organism=organism)
#for n in range(len(new_quant_df['seq5'].iloc[0])):
# new_quant_df['Base 5-'+str(n)] = [x[n] for x in new_quant_df['seq5']]
#for n in range(len(new_quant_df['seq3'].iloc[0])):
# new_quant_df['Base 3-'+str(n)] = [x[n] for x in new_quant_df['seq3']]
#new_quant_df = new_quant_df.drop(['seq5','seq3'], axis=1)
new_quant_df = SP.find_score_branches_ppy(
new_quant_df, '/home/jordan/GENOMES/S288C/S288C_branches2.txt',
fa_dict)
return new_quant_df
'''Usage: python process_juncbase.py juncbase_output gff3_file fasta_file prefix
Please note: uses chr# format for chromosome names.'''
import sys
sys.path.insert(0, '/Users/jordanburke/RNA-is-awesome/')
sys.path.insert(0, '/home/jordan/RNA-is-awesome/')
sys.path.insert(0, '/home/jordan/CodeBase/RNA-is-awesome')
import SPTools as SP
juncbase_output = sys.argv[1]
gff3_file = sys.argv[2]
print gff3_file
fasta_file = sys.argv[3]
print fasta_file
prefix = sys.argv[4]
fasta_dict = SP.make_fasta_dict(fasta_file)
junc_df, sample_list = SP.read_juncbase_output(juncbase_output)
seq_df = SP.get_junction_sequence(junc_df, gff3_file, fasta_dict)
pos_matrix_5prime, pos_matrix_3prime = SP.generate_consensus_matrix(gff3_file, fasta_dict, PSSM=True)
scored_df = SP.score_new_sites(seq_df, pos_matrix_5prime, pos_matrix_3prime, PSSM=True)
filt_df1, filt_df2 = SP.reformat_df(scored_df, sample_list)
#intron_ret_df = filt_df[filt_df['as_event_type'] == 'intron_retention']
#intron_ret_df = intron_ret_df.reset_index(drop=True)
#alt_donor = filt_df[filt_df['as_event_type'] == 'alternative_donor']
#alt_acceptor = filt_df[filt_df['as_event_type'] == 'alternative_acceptor']
filt_df1.to_csv('{0}_seq_score.tsv'.format(prefix), sep='\t', float_format='%.2f')
filt_df2.to_csv('{0}_PSI.tsv'.format(prefix), sep='\t', float_format='%.2f')
